Fine-Tuning Approach for Segmentation of Gliomas in Brain Magnetic Resonance Images with a Machine Learning Method to Normalize Image Differences among Facilities

Automatic assessment of disproportionately enlarged subarachnoid-space hydrocephalus from 3D MRI using two deep learning models

Background

Disproportionately enlarged subarachnoid-space hydrocephalus (DESH) is a key feature for Hakim disease (idiopathic normal pressure hydrocephalus: iNPH), but subjectively evaluated. To develop automatic quantitative assessment of DESH with automatic segmentation using combined deep learning models.

Methods

This study included 180 participants (42 Hakim patients, 138 healthy volunteers; 78 males, 102 females). Overall, 159 three-dimensional (3D) T1-weighted and 180 T2-weighted MRIs were included. As a semantic segmentation, 3D MRIs were automatically segmented in the total ventricles, total subarachnoid space (SAS), high-convexity SAS, and Sylvian fissure and basal cistern on the 3D U-Net model. As an image classification, DESH, ventricular dilatation (VD), tightened sulci in the high convexities (THC), and Sylvian fissure dilatation (SFD) were automatically assessed on the multimodal convolutional neural network (CNN) model. For both deep learning models, 110 T1- and 130 T2-weighted MRIs were used for training, 30 T1- and 30 T2-weighted MRIs for internal validation, and the remaining 19 T1- and 20 T2-weighted MRIs for external validation. Dice score was calculated as (overlapping area) × 2/total area.

Results

Automatic region extraction from 3D T1- and T2-weighted MRI was accurate for the total ventricles (mean Dice scores: 0.85 and 0.83), Sylvian fissure and basal cistern (0.70 and 0.69), and high-convexity SAS (0.68 and 0.60), respectively. Automatic determination of DESH, VD, THC, and SFD from the segmented regions on the multimodal CNN model was sufficiently reliable; all of the mean softmax probability scores were exceeded by 0.95. All of the areas under the receiver-operating characteristic curves of the DESH, Venthi, and Sylhi indexes calculated by the segmented regions for detecting DESH were exceeded by 0.97.

Conclusion

Using 3D U-Net and a multimodal CNN, DESH was automatically detected with automatically segmented regions from 3D MRIs. Our developed diagnostic support tool can improve the precision of Hakim disease (iNPH) diagnosis.

Multi-modal brain tumor segmentation via conditional synthesis with Fourier domain adaptation

Accurate brain tumor segmentation is critical for diagnosis and treatment planning, whereby multi-modal magnetic resonance imaging (MRI) is typically used for analysis. However, obtaining all required sequences and expertly labeled data for training is challenging and can result in decreased quality of segmentation models developed through automated algorithms. In this work, we examine the possibility of employing a conditional generative adversarial network (GAN) approach for synthesizing multi-modal images to train deep learning-based neural networks aimed at high-grade glioma (HGG) segmentation. The proposed GAN is conditioned on auxiliary brain tissue and tumor segmentation masks, allowing us to attain better accuracy and control of tissue appearance during synthesis. To reduce the domain shift between synthetic and real MR images, we additionally adapt the low-frequency Fourier space components of synthetic data, reflecting the style of the image, to those of real data. We demonstrate the impact of Fourier domain adaptation (FDA) on the training of 3D segmentation networks and attain significant improvements in both the segmentation performance and prediction confidence. Similar outcomes are seen when such data is used as a training augmentation alongside the available real images. In fact, experiments on the BraTS2020 dataset reveal that models trained solely with synthetic data exhibit an improvement of up to 4% in Dice score when using FDA, while training with both real and FDA-processed synthetic data through augmentation results in an improvement of up to 5% in Dice compared to using real data alone. This study highlights the importance of considering image frequency in generative approaches for medical image synthesis and offers a promising approach to address data scarcity in medical imaging segmentation.

Applications of Machine Learning (ML) and Mathematical Modeling (MM) in Healthcare with Special Focus on Cancer Prognosis and Anticancer Therapy: Current Status and Challenges

The use of data-driven high-throughput analytical techniques, which has given rise to computational oncology, is undisputed. The widespread use of machine learning (ML) and mathematical modeling (MM)-based techniques is widely acknowledged. These two approaches have fueled the advancement in cancer research and eventually led to the uptake of telemedicine in cancer care. For diagnostic, prognostic, and treatment purposes concerning different types of cancer research, vast databases of varied information with manifold dimensions are required, and indeed, all this information can only be managed by an automated system developed utilizing ML and MM. In addition, MM is being used to probe the relationship between the pharmacokinetics and pharmacodynamics (PK/PD interactions) of anti-cancer substances to improve cancer treatment, and also to refine the quality of existing treatment models by being incorporated at all steps of research and development related to cancer and in routine patient care. This review will serve as a consolidation of the advancement and benefits of ML and MM techniques with a special focus on the area of cancer prognosis and anticancer therapy, leading to the identification of challenges (data quantity, ethical consideration, and data privacy) which are yet to be fully addressed in current studies.

Learning technology for detection and grading of cancer tissue using tumour ultrasound images1

BACKGROUND

Early diagnosis of breast cancer is crucial to perform effective therapy. Many medical imaging modalities including MRI, CT, and ultrasound are used to diagnose cancer.

OBJECTIVE

This study aims to investigate feasibility of applying transfer learning techniques to train convoluted neural networks (CNNs) to automatically diagnose breast cancer via ultrasound images.

METHODS

Transfer learning techniques helped CNNs recognise breast cancer in ultrasound images. Each model's training and validation accuracies were assessed using the ultrasound image dataset. Ultrasound images educated and tested the models.

RESULTS

MobileNet had the greatest accuracy during training and DenseNet121 during validation. Transfer learning algorithms can detect breast cancer in ultrasound images.

CONCLUSIONS

Based on the results, transfer learning models may be useful for automated breast cancer diagnosis in ultrasound images. However, only a trained medical professional should diagnose cancer, and computational approaches should only be used to help make quick decisions.

Noninvasive grading of glioma brain tumors using magnetic resonance imaging and deep learning methods

PURPOSE

Convolutional Neural Networks (ConvNets) have quickly become popular machine learning techniques in recent years, particularly in the classification and segmentation of medical images. One of the most prevalent types of brain cancers is glioma, and early, accurate diagnosis is essential for both treatment and survival. In this study, MRI scans were examined utilizing deep learning techniques to examine glioma diagnosis studies.

METHODS

In this systematic review, keywords were used to obtain English-language studies from the Arxiv, IEEE, Springer, ScienceDirect, and PubMed databases for the years 2010-2022. The material needed for review was then collected from the articles once they had been chosen based on the entry and exit criteria and in accordance with the research's goal.

RESULTS

Finally, 77 different academic articles were chosen. According to a study of published articles, glioma brain tumors were discovered, categorized, and segmented utilizing a coordinated approach that included image collecting, pre-processing, model design and execution, and model output evaluation. The majority of investigations have used publicly accessible photo databases and already-trained algorithms. The bulk of studies have employed Dice's classification accuracy and similarity coefficient metrics to assess model performance.

CONCLUSION

The results of this study indicate that glioma segmentation has received more attention from researchers than glioma detection and classification. It is advised that more research be done in the areas of glioma detection and, particularly, grading in order to be included in systems that support medical diagnosis.

Qualitative MR features to identify non-enhancing tumors within glioblastoma's T2-FLAIR hyperintense lesions

PURPOSE

To identify qualitative MRI features of non-(contrast)-enhancing tumor (nCET) in glioblastoma's T2-FLAIR hyperintense lesion.

METHODS

Thirty-three histologically confirmed glioblastoma patients whose T1-, T2- and contrast-enhanced T1-weighted MRI and 11C-methionine positron emission tomography (Met-PET) were available were included in this study. Met-PET was utilized as a surrogate for tumor burden. Imaging features for identifying nCET were searched by qualitative examination of 156 targets. A new scoring system to identify nCET was established and validated by two independent observers.

RESULTS

Three imaging features were found helpful for identifying nCET; "Bulky gray matter involvement", "Around the rim of contrast-enhancement (Around-rim)," and "High-intensity on T1WI and low-intensity on T2WI (HighT1LowT2)" resulting in an nCET score = 2 × Bulky gray matter involvement - 2 × Around-rim + HighT1LowT2 + 2. The nCET score's classification performances of two independent observers measured by AUC were 0.78 and 0.80, with sensitivities and specificities using a threshold of four being 0.443 and 0.771, and 0.916 and 0.768, respectively. The weighted kappa coefficient for the nCET score was 0.946.

CONCLUSION

The current investigation demonstrated that qualitative assessments of glioblastoma's MRI might help identify nCET in T2/FLAIR high-intensity lesions. The novel nCET score is expected to aid in expanding treatment targets within the T2/FLAIR high-intensity lesions.

Current role of machine learning and radiogenomics in precision neuro-oncology

In the past few years, artificial intelligence (AI) has been increasingly used to create tools that can enhance workflow in medicine. In particular, neuro-oncology has benefited from the use of AI and especially machine learning (ML) and radiogenomics, which are subfields of AI. ML can be used to develop algorithms that dynamically learn from available medical data in order to automatically do specific tasks. On the other hand, radiogenomics can identify relationships between tumor genetics and imaging features, thus possibly giving new insights into the pathophysiology of tumors. Therefore, ML and radiogenomics could help treatment tailoring, which is crucial in personalized neuro-oncology. The aim of this review is to illustrate current and possible future applications of ML and radiomics in neuro-oncology.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Prediction of cervical lymph node metastasis from immunostained specimens of tongue cancer using a multilayer perceptron neural network

BACKGROUND

Although cervical lymph node metastasis is an important prognostic factor for oral cancer, occult metastases remain undetected even by diagnostic imaging. We developed a learning model to predict lymph node metastasis in resected specimens of tongue cancer by classifying the level of immunohistochemical (IHC) staining for angiogenesis- and lymphangiogenesis-related proteins using a multilayer perceptron neural network (MNN).

METHODS

We obtained a dataset of 76 patients with squamous cell carcinoma of the tongue who had undergone primary tumor resection. All 76 specimens were IHC stained for the six types shown above (VEGF-C, VEGF-D, NRP1, NRP2, CCR7, and SEMA3E) and 456 slides were prepared. We scored the staining levels visually on all slides. We created virtual slides (4560 images) and the accuracy of the MNN model was verified by comparing it with a hue-saturation (HS) histogram, which quantifies the manually determined visual information.

RESULTS

The accuracy of the training model with the MNN was 98.6%, and when the training image was converted to grayscale, the accuracy decreased to 52.9%. This indicates that our MNN adequately evaluates the level of staining rather than the morphological features of the IHC images. Multivariate analysis revealed that CCR7 staining level and T classification were independent factors associated with the presence of cervical lymph node metastasis in both HS histograms and MNN.

CONCLUSION

These results suggest that IHC assessment using MNN may be useful for identifying lymph node metastasis in patients with tongue cancer.

Application of artificial intelligence for automatic cataract staging based on anterior segment images: comparing automatic segmentation approaches to manual segmentation

Purpose

Cataract is one of the leading causes of blindness worldwide, accounting for >50% of cases of blindness in low- and middle-income countries. In this study, two artificial intelligence (AI) diagnosis platforms are proposed for cortical cataract staging to achieve a precise diagnosis.

Methods

A total of 647 high quality anterior segment images, which included the four stages of cataracts, were collected into the dataset. They were divided randomly into a training set and a test set using a stratified random-allocation technique at a ratio of 8:2. Then, after automatic or manual segmentation of the lens area of the cataract, the deep transform-learning (DTL) features extraction, PCA dimensionality reduction, multi-features fusion, fusion features selection, and classification models establishment, the automatic and manual segmentation DTL platforms were developed. Finally, the accuracy, confusion matrix, and area under the receiver operating characteristic (ROC) curve (AUC) were used to evaluate the performance of the two platforms.

Results

In the automatic segmentation DTL platform, the accuracy of the model in the training and test sets was 94.59 and 84.50%, respectively. In the manual segmentation DTL platform, the accuracy of the model in the training and test sets was 97.48 and 90.00%, respectively. In the test set, the micro and macro average AUCs of the two platforms reached >95% and the AUC for each classification was >90%. The results of a confusion matrix showed that all stages, except for mature, had a high recognition rate.

Conclusion

Two AI diagnosis platforms were proposed for cortical cataract staging. The resulting automatic segmentation platform can stage cataracts more quickly, whereas the resulting manual segmentation platform can stage cataracts more accurately.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.

MRI-Based Radiomics Differentiates Skull Base Chordoma and Chondrosarcoma: A Preliminary Study

Simple Summary

In this study, we created a novel MRI-based machine learning model to differentiate skull base chordoma and chondrosarcoma with multiparametric signatures. While these tumors share common radiographic characteristics, clinical behavior is distinct. Therefore, distinguishing these tumors before initial surgical intervention would be useful, potentially impacting the surgical strategy. Although there are some limitations, such as the risk of overfitting and the lack of an extramural cohort for truly independent final validation, our machine learning model distinguishing chordoma from chondrosarcoma yielded superior diagnostic accuracy to that achieved by 20 board-certified neurosurgeons.

Abstract

Chordoma and chondrosarcoma share common radiographic characteristics yet are distinct clinically. A radiomic machine learning model differentiating these tumors preoperatively would help plan surgery. MR images were acquired from 57 consecutive patients with chordoma (N = 32) or chondrosarcoma (N = 25) treated at the University of Tokyo Hospital between September 2012 and February 2020. Preoperative T1-weighted images with gadolinium enhancement (GdT1) and T2-weighted images were analyzed. Datasets from the first 47 cases were used for model creation, and those from the subsequent 10 cases were used for validation. Feature extraction was performed semi-automatically, and 2438 features were obtained per image sequence. Machine learning models with logistic regression and a support vector machine were created. The model with the highest accuracy incorporated seven features extracted from GdT1 in the logistic regression. The average area under the curve was 0.93 ± 0.06, and accuracy was 0.90 (9/10) in the validation dataset. The same validation dataset was assessed by 20 board-certified neurosurgeons. Diagnostic accuracy ranged from 0.50 to 0.80 (median 0.60, 95% confidence interval 0.60 ± 0.06%), which was inferior to that of the machine learning model (p = 0.03), although there are some limitations, such as the risk of overfitting and the lack of an extramural cohort for truly independent final validation. In summary, we created a novel MRI-based machine learning model to differentiate skull base chordoma and chondrosarcoma from multiparametric signatures.

Automated brain tumour identification using magnetic resonance imaging: a systematic review and meta-analysis

Background

Automated brain tumor identification facilitates diagnosis and treatment planning. We evaluate the performance of traditional machine learning (TML) and deep learning (DL) in brain tumor detection and segmentation, using MRI.

Methods

A systematic literature search from January 2000 to May 8, 2021 was conducted. Study quality was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Detection meta-analysis was performed using a unified hierarchical model. Segmentation studies were evaluated using a random effects model. Sensitivity analysis was performed for externally validated studies.

Results

Of 224 studies included in the systematic review, 46 segmentation and 38 detection studies were eligible for meta-analysis. In detection, DL achieved a lower false positive rate compared to TML; 0.018 (95% CI, 0.011 to 0.028) and 0.048 (0.032 to 0.072) (P < .001), respectively. In segmentation, DL had a higher dice similarity coefficient (DSC), particularly for tumor core (TC); 0.80 (0.77 to 0.83) and 0.63 (0.56 to 0.71) (P < .001), persisting on sensitivity analysis. Both manual and automated whole tumor (WT) segmentation had “good” (DSC ≥ 0.70) performance. Manual TC segmentation was superior to automated; 0.78 (0.69 to 0.86) and 0.64 (0.53 to 0.74) (P = .014), respectively. Only 30% of studies reported external validation.

Conclusions

The comparable performance of automated to manual WT segmentation supports its integration into clinical practice. However, manual outperformance for sub-compartmental segmentation highlights the need for further development of automated methods in this area. Compared to TML, DL provided superior performance for detection and sub-compartmental segmentation. Improvements in the quality and design of studies, including external validation, are required for the interpretability and generalizability of automated models.

Automated Endocardial Border Detection and Left Ventricular Functional Assessment in Echocardiography Using Deep Learning

Endocardial border detection is a key step in assessing left ventricular systolic function in echocardiography. However, this process is still not sufficiently accurate, and manual retracing is often required, causing time-consuming and intra-/inter-observer variability in clinical practice. To address these clinical issues, more accurate and normalized automatic endocardial border detection would be valuable. Here, we develop a deep learning-based method for automated endocardial border detection and left ventricular functional assessment in two-dimensional echocardiographic videos. First, segmentation of the left ventricular cavity was performed in the six representative projections for a cardiac cycle. We employed four segmentation methods: U-Net, UNet++, UNet3+, and Deep Residual U-Net. UNet++ and UNet3+ showed a sufficiently high performance in the mean value of intersection over union and Dice coefficient. The accuracy of the four segmentation methods was then evaluated by calculating the mean value for the estimation error of the echocardiographic indexes. UNet++ was superior to the other segmentation methods, with the acceptable mean estimation error of the left ventricular ejection fraction of 10.8%, global longitudinal strain of 8.5%, and global circumferential strain of 5.8%, respectively. Our method using UNet++ demonstrated the best performance. This method may potentially support examiners and improve the workflow in echocardiography.

BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images

Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise and acoustic shadow, always degenerate the detection accuracy. In this study, we developed a deep learning model called BUSnet to detect the breast tumor lesions in US images with high accuracy. We first developed a two-stage method including the unsupervised region proposal and bounding-box regression algorithms. Then, we proposed a post-processing method to enhance the detecting accuracy further. The proposed method was used to a benchmark dataset, which includes 487 benign samples and 210 malignant samples. The results proved the effectiveness and accuracy of the proposed method.

Single-Cell Analysis Using Machine Learning Techniques and Its Application to Medical Research

In recent years, the diversity of cancer cells in tumor tissues as a result of intratumor heterogeneity has attracted attention. In particular, the development of single-cell analysis technology has made a significant contribution to the field; technologies that are centered on single-cell RNA sequencing (scRNA-seq) have been reported to analyze cancer constituent cells, identify cell groups responsible for therapeutic resistance, and analyze gene signatures of resistant cell groups. However, although single-cell analysis is a powerful tool, various issues have been reported, including batch effects and transcriptional noise due to gene expression variation and mRNA degradation. To overcome these issues, machine learning techniques are currently being introduced for single-cell analysis, and promising results are being reported. In addition, machine learning has also been used in various ways for single-cell analysis, such as single-cell assay of transposase accessible chromatin sequencing (ATAC-seq), chromatin immunoprecipitation sequencing (ChIP-seq) analysis, and multi-omics analysis; thus, it contributes to a deeper understanding of the characteristics of human diseases, especially cancer, and supports clinical applications. In this review, we present a comprehensive introduction to the implementation of machine learning techniques in medical research for single-cell analysis, and discuss their usefulness and future potential.

Prostate Cancer Radiogenomics-From Imaging to Molecular Characterization

Radiomics and genomics represent two of the most promising fields of cancer research, designed to improve the risk stratification and disease management of patients with prostate cancer (PCa). Radiomics involves a conversion of imaging derivate quantitative features using manual or automated algorithms, enhancing existing data through mathematical analysis. This could increase the clinical value in PCa management. To extract features from imaging methods such as magnetic resonance imaging (MRI), the empiric nature of the analysis using machine learning and artificial intelligence could help make the best clinical decisions. Genomics information can be explained or decoded by radiomics. The development of methodologies can create more-efficient predictive models and can better characterize the molecular features of PCa. Additionally, the identification of new imaging biomarkers can overcome the known heterogeneity of PCa, by non-invasive radiological assessment of the whole specific organ. In the future, the validation of recent findings, in large, randomized cohorts of PCa patients, can establish the role of radiogenomics. Briefly, we aimed to review the current literature of highly quantitative and qualitative results from well-designed studies for the diagnoses, treatment, and follow-up of prostate cancer, based on radiomics, genomics and radiogenomics research.

Application of Artificial Intelligence in COVID-19 Diagnosis and Therapeutics

The coronavirus disease 2019 (COVID-19) pandemic began at the end of December 2019, giving rise to a high rate of infections and causing COVID-19-associated deaths worldwide. It was first reported in Wuhan, China, and since then, not only global leaders, organizations, and pharmaceutical/biotech companies, but also researchers, have directed their efforts toward overcoming this threat. The use of artificial intelligence (AI) has recently surged internationally and has been applied to diverse aspects of many problems. The benefits of using AI are now widely accepted, and many studies have shown great success in medical research on tasks, such as the classification, detection, and prediction of disease, or even patient outcome. In fact, AI technology has been actively employed in various ways in COVID-19 research, and several clinical applications of AI-equipped medical devices for the diagnosis of COVID-19 have already been reported. Hence, in this review, we summarize the latest studies that focus on medical imaging analysis, drug discovery, and therapeutics such as vaccine development and public health decision-making using AI. This survey clarifies the advantages of using AI in the fight against COVID-19 and provides future directions for tackling the COVID-19 pandemic using AI techniques.

Reverse Engineering Glioma Radiomics to Conventional Neuroimaging

A novel radiological research field pursuing comprehensive quantitative image, namely “Radiomics,” gained traction along with the advancement of computational technology and artificial intelligence. This novel concept for analyzing medical images brought extensive interest to the neuro-oncology and neuroradiology research community to build a diagnostic workflow to detect clinically relevant genetic alteration of gliomas noninvasively. Although quite a few promising results were published regarding MRI-based diagnosis of isocitrate dehydrogenase (IDH) mutation in gliomas, it has become clear that an ample amount of effort is still needed to render this technology clinically applicable. At the same time, many significant insights were discovered through this research project, some of which could be “reverse engineered” to improve conventional non-radiomic MR image acquisition. In this review article, the authors aim to discuss the recent advancements and encountering issues of radiomics, how we can apply the knowledge provided by radiomics to standard clinical images, and further expected technological advances in the realm of radiomics and glioma.

Assessing Versatile Machine Learning Models for Glioma Radiogenomic Studies across Hospitals

Simple Summary

Radiogenomics enables prediction of the status and prognosis of patients using non-invasively obtained imaging data. Current machine learning (ML) methods used in radiogenomics require huge datasets, which involve the handling of large heterogeneous datasets from multiple cohorts/hospitals. In this study, two different glioma datasets were used to test various ML and image pre-processing methods to confirm whether the models trained on one dataset are universally applicable to other datasets. Our result suggested that the ML method that yielded the highest accuracy in a single dataset was likely to be overfitted. We demonstrated that implementation of standardization and dimension reduction procedures prior to classification, enabled the development of ML methods that are less affected by the multiple cohort difference. We advocate using caution in interpreting the results of radiogenomic studies of the training and testing datasets that are small or mixed, with a view to implementing practical ML methods in radiogenomics.

Abstract

Radiogenomics use non-invasively obtained imaging data, such as magnetic resonance imaging (MRI), to predict critical biomarkers of patients. Developing an accurate machine learning (ML) technique for MRI requires data from hundreds of patients, which cannot be gathered from any single local hospital. Hence, a model universally applicable to multiple cohorts/hospitals is required. We applied various ML and image pre-processing procedures on a glioma dataset from The Cancer Image Archive (TCIA, n = 159). The models that showed a high level of accuracy in predicting glioblastoma or WHO Grade II and III glioma using the TCIA dataset, were then tested for the data from the National Cancer Center Hospital, Japan (NCC, n = 166) whether they could maintain similar levels of high accuracy. Results: we confirmed that our ML procedure achieved a level of accuracy (AUROC = 0.904) comparable to that shown previously by the deep-learning methods using TCIA. However, when we directly applied the model to the NCC dataset, its AUROC dropped to 0.383. Introduction of standardization and dimension reduction procedures before classification without re-training improved the prediction accuracy obtained using NCC (0.804) without a loss in prediction accuracy for the TCIA dataset. Furthermore, we confirmed the same tendency in a model for IDH1/2 mutation prediction with standardization and application of dimension reduction that was also applicable to multiple hospitals. Our results demonstrated that overfitting may occur when an ML method providing the highest accuracy in a small training dataset is used for different heterogeneous data sets, and suggested a promising process for developing an ML method applicable to multiple cohorts.

Towards Clinical Application of Artificial Intelligence in Ultrasound Imaging

Artificial intelligence (AI) is being increasingly adopted in medical research and applications. Medical AI devices have continuously been approved by the Food and Drug Administration in the United States and the responsible institutions of other countries. Ultrasound (US) imaging is commonly used in an extensive range of medical fields. However, AI-based US imaging analysis and its clinical implementation have not progressed steadily compared to other medical imaging modalities. The characteristic issues of US imaging owing to its manual operation and acoustic shadows cause difficulties in image quality control. In this review, we would like to introduce the global trends of medical AI research in US imaging from both clinical and basic perspectives. We also discuss US image preprocessing, ingenious algorithms that are suitable for US imaging analysis, AI explainability for obtaining informed consent, the approval process of medical AI devices, and future perspectives towards the clinical application of AI-based US diagnostic support technologies.

Integrated Analysis of Whole Genome and Epigenome Data Using Machine Learning Technology: Toward the Establishment of Precision Oncology

With the completion of the International Human Genome Project, we have entered what is known as the post-genome era, and efforts to apply genomic information to medicine have become more active. In particular, with the announcement of the Precision Medicine Initiative by U.S. President Barack Obama in his State of the Union address at the beginning of 2015, "precision medicine," which aims to divide patients and potential patients into subgroups with respect to disease susceptibility, has become the focus of worldwide attention. The field of oncology is also actively adopting the precision oncology approach, which is based on molecular profiling, such as genomic information, to select the appropriate treatment. However, the current precision oncology is dominated by a method called targeted-gene panel (TGP), which uses next-generation sequencing (NGS) to analyze a limited number of specific cancer-related genes and suggest optimal treatments, but this method causes the problem that the number of patients who benefit from it is limited. In order to steadily develop precision oncology, it is necessary to integrate and analyze more detailed omics data, such as whole genome data and epigenome data. On the other hand, with the advancement of analysis technologies such as NGS, the amount of data obtained by omics analysis has become enormous, and artificial intelligence (AI) technologies, mainly machine learning (ML) technologies, are being actively used to make more efficient and accurate predictions. In this review, we will focus on whole genome sequencing (WGS) analysis and epigenome analysis, introduce the latest results of omics analysis using ML technologies for the development of precision oncology, and discuss the future prospects.

A New Era of Neuro-Oncology Research Pioneered by Multi-Omics Analysis and Machine Learning

Although the incidence of central nervous system (CNS) cancers is not high, it significantly reduces a patient’s quality of life and results in high mortality rates. A low incidence also means a low number of cases, which in turn means a low amount of information. To compensate, researchers have tried to increase the amount of information available from a single test using high-throughput technologies. This approach, referred to as single-omics analysis, has only been partially successful as one type of data may not be able to appropriately describe all the characteristics of a tumor. It is presently unclear what type of data can describe a particular clinical situation. One way to solve this problem is to use multi-omics data. When using many types of data, a selected data type or a combination of them may effectively resolve a clinical question. Hence, we conducted a comprehensive survey of papers in the field of neuro-oncology that used multi-omics data for analysis and found that most of the papers utilized machine learning techniques. This fact shows that it is useful to utilize machine learning techniques in multi-omics analysis. In this review, we discuss the current status of multi-omics analysis in the field of neuro-oncology and the importance of using machine learning techniques.